© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 9094
    Prev
    Next
    INDEX
    Explanations

    terms related to external communities and group dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.43
     tacón
    -0.37
     *)__
    -0.34
    baiki
    -0.32
    RTEE
    -0.32
     conflit
    -0.31
    министра
    -0.31
     ""],
    -0.30
    </thead>
    -0.30
    geslacht
    -0.30
    POSITIVE LOGITS
     outside
    1.59
     Outside
    1.52
    outside
    1.47
     OUTSIDE
    1.44
    Outside
    1.43
     external
    1.35
     exterior
    1.27
    OUTSIDE
    1.27
     External
    1.22
     afuera
    1.22
    Activations Density 0.979%

    No Known Activations